Training a machine learning / deep learning model is one thing and deploying it to a production is completely different beast. Not only you have to deploy it to a production, but you will have to retrain the model every now and then and redeploy the updates. With many machine learning / deep learning projects / POCs running in parallel with multiple environments such as dev, test prod, managing model life cycle from training to deployment can quickly become overwhelming. In this talk, I will discuss an approach to handle this complexity using Docker and Python. Rough outline of the talk is,

• Introduction to the topic
• Problem statement
• Quick introduction to Docker
• Discussing the proposed architecture
• Alternative architecture using AWS infrastructure
• Demo

Reinforcement Learning algorithms becoming more and more sophisticated every day which is evident from the recent win of AlphaGo and AlphaGo Zero (https://deepmind.com/blog/alphago-zero-learning-scratch/ ). OpenAI has provided toolkit openai gym for research and development of Reinforcement Learning algorithms.

In this workshop, we will focus on introduction to the basic concepts and algorithms in Reinforcement Learning and hands on coding.

Content

• Introduction to Reinforcement Learning Concepts and teminologies
• Setting up OpenAI Gym and other dependencies
• Introducing OpenAI Gym and its APIs
• Implementing simple algorithms using couple of OpenAI Gym Environments
• Demo of Deep Reinforcement Learning using one of the OpenAI Gym Atari game

Python ecosystem for Natural language processing has evolved in last decade and rich set of open source tools and data sets are now available.

In this session, we will go over basics of Natural language processing along with sample code demonstration and hands on tutorials using following famous python libraries,

1. NLTK : One of the oldest and famous library for natural language analysis for researchers
2. Stanford CoreNLP : Production ready NLP library. (Written in java but has many open source python wrappers)
3. SpaCy: Comparatively new python NLP toolkit marketed as 'Industrial Strength' python library.

Session will introduce the various use cases and basic concepts related to the natural language processing with demo and hands on tutorials

Following NLP fundamentals will be discussed,

- Syntax Vs. Semantics

- Regular Expressions (Demo and Hands on)

- Word Embeddings (Demo and Hands on)

- Word Tokenization (Demo and Hands on)

- Part of Speech Tagging (Demo and Hands on)

- Text Similarity (Demo and Hands on)

- Text Summarization

- Named Entity Recognition ((Demo and Hands on))

- Sentiment Analysis (Demo and Hands on)